CV & Deep learning on IBM RedHat OpenShift

1. CV & Deep learning on RedHat OpenShift Yoga Pose Estimation March 4 2020 Grant Steinfeld IBM Model Asset Exchange Tensor Flow Modeling Human Poses How does OpenShift help? Using IBM CODAIT Technical Introduction Go to GitHub 1st  https://bit.ly/38sjLHz

2. Computer Vision(CV) 2

3. Not always perfect! IBM Artificial Intelligence / CODAIT 3

4. Login/Sign up => IBM Cloud Account https://ibm.biz/BdqDVL

5. Link your Cluster to your IBM id https://os4yogait.mybluemix.net/ IBM Artificial Intelligence / CODAIT 5

6. IBM Artificial Intelligence / CODAIT 7 The Model Asset eXchange (MAX) on IBM Developer is a place for developers to find and use free, open source, state-of-the-art deep learning models for common application domains, such as text, image, audio, and video processing.

7. IBM Artificial Intelligence / CODAIT 8

8. Black box IBM Artificial Intelligence / CODAIT 9

9. Exploring deployable models 10 • IoT • Serverless • Object Detection • Audio • Video • Posture • Yoga Poses • Exercise mentoring ( Mirror )

10. Image Recognition 11 IBM Artificial Intelligence / CODAIT COCO – Common Objects in Contect http://cocodataset.org/#explore Deformable Convolutional Networks - Jifeng Dai et al http://presentations.cocodataset.org/COCO17-Detect-MSRA.pdf Pattern Analysis Statistical Modelling and Computational Learning (PASCAL2) http://host.robots.ox.ac.uk/pascal/VOC/voc2012/

11. Lab 1 – Image Classifier to OpenShift3 IBM Artificial Intelligence / CODAIT 12 Login to you cloud account Change to 1840867 account Locate your OpenShift 3 cluster Open web console Create Project __>>> maximagec Browse Catalog/Deploy Image/image name __>>> codait/max-object-detector Create a route https://developer.ibm.com/tutorials/deploy-a-model-asset-exchange-microservice-on-red-hat-openshift/

12. IBM Artificial Intelligence / CODAIT 13

13. IBM Artificial Intelligence / CODAIT 14

14. Navigate to the Public URL and test out the classifier

15. IBM Artificial Intelligence / CODAIT 16

16. IBM Artificial Intelligence / CODAIT 17

17. `A neural network is a function that learns the expected output for a given input from training datasets` 18 predictive mode https://marutitech.com/working-image-recognition/

18. IBM Artificial Intelligence / CODAIT 19 https://www.mathworks.com/solutions/deep-learning/features.html?s_eid=PSM_15028 https://www.youtube.com/watch?v=3cSjsTKtN9M MATLAB - MATHWORKS

19. Lab 2 / Follow along Yoga pose estimator DEMO! Yogait

20. Go to this repo local docker https://bit.ly/38sjLHz IBM Artificial Intelligence / CODAIT 21

21. Resources IBM Artificial Intelligence / CODAIT 22 https://www.tensorflow.org/ https://keras.io/ https://marutitech.com/working-image-recognition/

22. Thank you Grant Steinfeld @gsteinfeld developer.ibm.com © Copyright IBM Corporation 2019. All rights reserved. The information contained in these materials is provided for informational purposes only, and is provided AS IS without warranty of any kind, express or implied. Any statement of direction represents IBM's current intent, is subject to change or withdrawal, and represents only goals and objectives. IBM, the IBM logo, and other IBM products and services are trademarks of the International Business Machines Corporation, in the United States, other countries or both. Other company, product, or service names may be trademarks or service marks of others.

23. 24

Editor's Notes

Being able to go from idea to result with the least possible delay is key to doing good research. Image recognition refers to technologies that identify places, logos, people, objects, buildings, and several other variables in images. Users are sharing vast amounts of data through apps, social networks, and websites. Additionally, mobile phones equipped with cameras are leading to the creation of limitless digital images and videos. The large volume of digital data is being used by companies to deliver better and smarter services to the people accessing it Image recognition is a part of computer vision and a process to identify and detect an object or attribute in a digital video or image. Computer vision is a broader term which includes methods of gathering, processing and analyzing data from the real world. The data is high-dimensional and produces numerical or symbolic information in the form of decisions. Apart from image recognition, computer vision also includes event detection, object recognition, learning, image reconstruction and video tracking.
URL: https://os4yogait.mybluemix.netKey: oslabRegion: us-eastClusters: ~20Workers: 3 x b3c.4x16K8s Version: 3.11.161_openshift Note Please be sure to click: Prefill Cache button on the URL before your lab Don't forget you have your https://os4yogait.mybluemix.net/admin to see the status of the clusters too If you need a cloudshell you can use https://shell.cloud.ibm.com/. It should be attached to the IBMid, that the student will have created for your workshop. If you have issues with it though please ask questions in #cloudshell-users, we do not control it.
Key: ikslabRegion: us-eastClusters: ~20Workers: 3 x b3c.4x16K8s Version: 1.15.10 Note Please be sure to click: Prefill Cache button on the URL before your lab Don't forget you have your https://k8syogait.mybluemix.net/admin to see the status of the clusters too If you need a cloudshell you can use https://shell.cloud.ibm.com/. It should be attached to the IBMid, that the student will have created for your workshop. If you have issues with it though please ask questions in #cloudshell-users, we do not control it.
The curated list includes a broad selection of deployable (ready-to-use) models and trainable (customize-before-use) models.
The caller does not need to know anything about the deep learning model that powers the service, the framework that was used to implement and run the model, or the native model inputs or outputs because these details are hidden by the microservice.
Organizing data involves classification and feature extraction. The first step in image classification is to simplify the image by extracting important information and leaving out the rest. For example, in the below image if you want to extract cat from the background you will notice a significant variation in RGB pixel values. However, by running an edge detector on the image we can simplify it. You can still easily discern the circular shape of the face and eyes in these edge images and so we can conclude that edge detection retains the essential information while throwing away non-essential information. Some well-known feature descriptor techniques are Haar-like features introduced by Viola and Jones, Histogram of Oriented Gradients (HOG), Scale-Invariant Feature Transform (SIFT), Speeded Up Robust Feature (SURF) etc.
http://cocodataset.org/#explore
To build a predictive model we need neural networks. The neural network is a system of hardware and software similar to our brain to estimate functions that depend on the huge amount of unknown inputs.
Deep Learning – Deep refers to the number of hidden layers typical 2 – 3 ( but can be +/– 150 )
Depth camera with Microsoft Kinect 360 experiments in 2013 ( before CV and MAX/CODAIT )
Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano. It was developed with a focus on enabling fast experimentation. Being able to go from idea to result with the least possible delay is key to doing good research. Use Keras if you need a deep learning library that: Allows for easy and fast prototyping (through user friendliness, modularity, and extensibility). Supports both convolutional networks and recurrent networks, as well as combinations of the two. Runs seamlessly on CPU and GPU.

CV & Deep learning on IBM RedHat OpenShift

Recommended

Recommended

More Related Content

What's hot

What's hot (20)

Similar to CV & Deep learning on IBM RedHat OpenShift

Similar to CV & Deep learning on IBM RedHat OpenShift (20)

Recently uploaded

Recently uploaded (20)

CV & Deep learning on IBM RedHat OpenShift

Editor's Notes